The Strategy Factory

An automated pipeline that transforms hypotheses into validated prediction market strategies. Seven stages, three statistical gates, zero tolerance for overfitting.

Why PM backtesting is different

In traditional quant trading, you backtest against 20 years of continuous price data for the same instrument. In prediction markets, every market is unique — born, lives briefly, resolves to 0 or 1, and dies. You can't backtest "a strategy on ECB March 2026." You backtest "a pattern across all ECB rate decisions as a class."

The Strategy Factory solves this by shifting the unit of analysis from instruments to event-type categories.

Seven stages, four gates

Every strategy flows through the same pipeline. At each gate, it either passes or is rejected. No exceptions, no shortcuts, no re-tuning after failure.

1
Hypothesis
Pattern identified
2
Formalize
14-field spec
3
Train
60% sample
GATE 1
4
Validate
20% held-out
GATE 2
5
Out-of-Sample
20% one-shot
GATE 3
6
Paper Trade
30+ events
GATE 4
7
Live
2% capital
The Factory in one sentence

An automated pipeline that transforms hypotheses into validated strategies, deploys the survivors with risk-controlled capital, monitors them against statistical benchmarks, and retires them when edge decays — while simultaneously developing replacements.

Three-sample testing for event markets

The classical mechanical trading system framework — Training, Validation, Out-of-Sample — adapted for prediction markets where samples are split across events, not time periods.

Training — 60%
Validation — 20%
OOS — 20%
Full optimization permitted. Overfitting expected.
NO parameter adjustment. Where overfitting dies.
One-shot. If it fails, the strategy is dead.
60%
Training
Parameter optimization on majority of historical events. Sharpe > 1.0, Win Rate > 55%, EV > 0. Profitable at +25% fee assumption.
20%
Validation
Held-out events. NO tuning allowed. Degradation must be < 50% from training. If it fails here: reject or return to hypothesis.
20%
Out-of-Sample
One-shot final test with realistic execution model. Profitable at +50% fee assumption. Fail = dead. No second chances. No re-tuning.

Why this works for small samples

Traditional quant backtesting uses thousands of data points. PM event categories have tens to hundreds. The Strategy Factory compensates with: conservative parameter selection (wide robustness windows), mandatory paper trading before live deployment, small initial position sizes (2% of capital), rapid feedback loops, and — critically — the Structural Event Clustering that pools structurally similar events across categories to increase effective sample sizes.

The initial ten strategies

First cohort entering the pipeline. Five verticals, 210-360 trade signals per year. Six exploit European information advantages. Three require German/French/Italian language access.

SF-ECB-001Training
ECB Reference Divergence
EU Monetary Policy · Polymarket
~65% win
3-5pp edge
8-12/yr
European Edge: OIS curve literacy rare among PM participants
SF-ECB-002Hypothesis
ECB Communication Drift
EU Monetary Policy · Polymarket
~60% win
2-4pp edge
10-20/yr
Language Edge: German/French/Italian speech sentiment inaccessible to US traders
SF-POL-001Hypothesis
Coalition Mathematics
EU Politics · Smarkets
~70% win
5-10pp edge
3-6/yr
European Edge: Koalitionsrechner, Brandmauer — US bots model "highest poll = winner"
SF-POL-002Hypothesis
EU Regulatory Milestone
EU Politics · Polymarket
~60% win
5-15pp edge
2-5/yr
European Edge: EU institutional knowledge (MiCA, DSA, ECJ)
SF-SPT-001Training
CL Pinnacle Spread
European Football · Smarkets
~55% win
2-4pp edge
100+/yr
Ref price access: Pinnacle closing line as oracle benchmark
SF-SPT-002Training
Bundesliga Info Edge
European Football · Smarkets
~60% win
3-6pp edge
30-60/yr
Language Edge: kicker.de, Transfermarkt, Bild — 2-6h before English propagation
SF-USD-001Validation
Fed Bond Strategy
US Economic Data · Kalshi
~95% win
5-7pp edge
8-10/yr
Near-certainty carry at 95¢+. 5% tail risk capped at 5% of capital.
SF-USD-002Hypothesis
CPI Nowcast Reference
US Economic Data · Kalshi
~60% win
Var. edge
12/yr
Cleveland Fed Nowcast as reference price for CPI bracket markets
SF-XPL-001Training
Cross-Platform Divergence
Cross-Platform · Polymarket + Kalshi
~80% win
2-4pp edge
20-40/yr
Settlement-rule-verified identical events with ≥5pp price difference
SF-WHL-001Hypothesis
Whale Signal Confirmation
Behavioural · Polymarket
~65% win
5-10pp edge
15-30/yr
2+ Blacklist wallets (P&L > $500K) taking same direction within 48h

Anti-overfitting rules

Overfitting is the primary risk in PM backtesting due to small sample sizes. These rules are system-enforced, not suggestions.

No re-tuning after validation failureReturn to hypothesis stage, not training. New specification required.
Out-of-sample is one-shotIf it fails, the strategy is dead. No second chances, regardless of backtest strength.
Fee sensitivity mandatoryEvery strategy must be profitable at +25% fees (validation) and +50% fees (OOS).
Parameter robustness windowOptimal parameters must remain profitable at ±15%. Cliff-edge parameters = overfitting.
Paper trading required30 events or 8 weeks minimum. No exceptions.
Max 15 live strategiesForces prioritization. Prevents capital dilution across too many marginal strategies.

The Factory is operational

v1.0 running since February 2026. First strategies in the pipeline. The methodology is proven — now being productized as infrastructure.

See the Innovation Layer → Trading Tools →